04 · doors · mixed

The 4 doors — deep dive

Each door is independent. Different storage backend, different signals, different UI surface, different status. Click a tab below to drill into a single door.

At a glance

Door	Storage	UI surface	Signal source	Status
Zeus fitness	Supabase	Lovable verocity	SQL view + helper	live · v0.1
Athena nutrition	Supabase	none (zombie)	stub (Phase J.2)	scaffold
Lakshmi finance	TradingV postgres	TradingV /rx-finance panel	SQL queries on TradingV	live · v0
Ganesh learning	markdown only	none (editor)	markdown helper	live · v0 · empty corpus

Zeus — fitness

The most mature door. Live since v0.1. Workouts logged through the verocity phone app land in Supabase. A SQL view exposes a 7-component drift score. A separate helper covers body composition. Recommendations write to Supabase and surface in the verocity app.

Drift composite (D-022 layering)

Fitness is the only door using a two-layer composite:

composite = 0.90 × view.drift + 0.10 × body_recomp_sub

The 7 in-view weights sum to 1.0. The composite blends view (90%) with body_recomp (10%).

Storage + UI

Markdown	`Zeus/rx/rx-YYYY-MM-DD-NN.md`
DB row	Supabase `recommendations` WHERE `domain='fitness'`
UI	Lovable verocity → Recommendations tab
Disposition	UI button → Supabase UPDATE → next `/rx-fitness` step 0.7 patches markdown
State files	`03_execution/current_plan.md`, `measurements.yaml`
Slash commands	`/rx-fitness`, `/rx-fitness-status`, `/rx-fitness-history`

Frontmatter schema (minimum required keys)

id: uuid
created_at: ISO8601
goal_ref: string (e.g. lift-vol-PR-2026Q3)
block_week: int
trigger: {type, signals_fired: [string]}
drift_score: float (0..1)
drift_breakdown: {pace, block_lag, gap_breach, load_drop, rpe_drift, recovery, conditioning, body_recomp}
confidence: int (0..100)
confidence_breakdown: {data_recency, signal_clarity, vault_corpus, dedup_distance}
status: open | snoozed | acted | dismissed
acted_disposition: acted_as_prescribed | acted_modified | skipped | dismissed
acted_at: ISO8601 | null
phase_w_synced_at: ISO8601 | null
verocity_rx_id: uuid (Supabase row pointer)
source_refs: [{path, score, quote}]
prior_open_recs: [{id, relation: reinforce|supersede|independent}]

Athena — nutrition

Scaffold mode only. Storage is wired (Supabase recommendations accepts domain='nutrition' rows), but the generator is unwired and there is no UI surface. The /rx-nutrition command runs in scaffold mode and emits a decision menu instead of a real rec.

Why it's a zombie

D-045 originally routed both fitness and nutrition through Lovable verocity. D-047 (operator directive, 2026-05-17) reversed that: Lovable surface = fitness only. So nutrition row format and table are ready, but no app reads them. Result: write-only storage with no consumer — a zombie.

Storage + UI

Markdown	`Athena/rx/SPEC.md` + planned `rx-nutr-*.md`
DB row	Supabase `recommendations` WHERE `domain='nutrition'` (planned, currently unused)
UI	none (D-047) — disposition channel UNRESOLVED (D-048 + Athena SPEC banner: 4 resolution options pending operator pick)
Disposition	TBD (Phase J.2) — see `Athena/rx/SPEC.md` 2026-05-19 banner. Pragmatist recommendation: markdown-only (mirror Ganesh learning).
State files	`state.md`, `profile.md`, `rules.md`, `meals.md`, `levers.md`
Slash command	`/rx-nutrition` — scaffold/decision-menu mode

Planned 5 signals (dormant until Phase J.2)

adherence_trend — compliance with macro plan over rolling window
macro_drift — actual macros vs target ratios
timing_consistency — meal-slot timing vs schedule
rotation_drift — repetition fatigue from same staples
appetite_drift — subjective hunger signal vs baseline

All five depend on a daily-log source the operator has not committed to yet. Phase J.2 ships when that decision is made.

Lakshmi — finance

The most data-rich door. Reads from the TradingV FastAPI app's local postgres — never Supabase. Hypotheses, opportunities, drift alerts, positions, and watchlist all feed the composite. Recs surface in a FastAPI /rx-finance panel.

Drift composite (~6 components)

Weights evolved with D-025/D-026 (concentration added, orphan lowered). Verify against current ~/.claude/commands/rx-finance.md before relying on exact values:

Weights are operator-tuned and may not sum to 1.0 verbatim — composite is normalised. Treat numbers here as illustrative; ground truth is in the slash command.

Storage + UI

Markdown	`Lakshmi/rx/rx-fin-YYYY-MM-DD-NN.md`
DB row	TradingV postgres `recommendations` WHERE `domain='finance'`
Write auth	`POST /v1/rx/recs` with header `X-RX-Ingest-Token`
Read auth	`GET /v1/rx/recs` with header `X-API-Key`
UI	TradingV FastAPI panel at `/rx-finance`
Disposition	UI button → `POST /v1/rx/recs/{id}/disposition` → next `/rx-finance` step 0.7 patches markdown
Outcome attribution	`trades.related_rec_id` FK closes loop into P&L (D-046)
Slash commands	`/rx-finance`, `/rx-finance-status`, `/rx-finance-history`

Dual-auth split. The ingest token can write but not read or disposition. The API key can read and disposition but cannot mass-ingest. This separation matters: the /rx-finance command runs with the ingest token only; the operator's UI uses the API key.

Known limitation (D-046). Hypothesis ↔ rec linkage uses a substring heuristic on body_md, which is false-positive prone. A rec mentioning "NVDA" matches every hypothesis whose slug contains "nvda" — even unrelated ones.

Ganesh — learning

The newest and lightest door. Markdown only forever in v0.x per D-047. No database, no Lovable surface, no FastAPI panel. The editor reads the file; the operator edits frontmatter to disposition.

Drift composite (5 components, flat)

Signals derive from heterogeneous markdown — active_sprints, _inbox, learning_log, notes.

Storage + UI

Markdown	`Ganesh/rx/rx-learn-YYYY-MM-DD-NN.md`
DB row	none — markdown is authoritative
UI	none — editor edits frontmatter directly
Disposition	`/rx-learning-status <id> <disposition>` edits frontmatter
State files	`02_library/active_sprints.md`, `_inbox/`, `03_execution/learning_log.md`, `02_library/notes/`
Vault scope	Indexer port `:8004`, cache `cache-learning.db`
Slash commands	`/rx-learning`, `/rx-learning-status`, `/rx-learning-history`

Empty corpus today. The learning vault scope is wired but contains zero ingested content. The vault bundle returns 0 results until the operator drops URLs in Videos/learning/_ingest_queue.md. The command sets thesis_match=0 and continues anyway.

Hard rule (D-047). Learning rx will never touch Lovable. If a local UI surface is built in the future it will be a separate store, not the Supabase recommendations table.

The cross-cutting commands

Four commands span doors. One is gated by action-rate data (rx-analyze).

Command	Purpose	Domain scope	Gate
`/rx-board`	Cross-domain timeline view — open recs, aging, forced-decision flags	fitness + finance + nutrition + learning 4-domain since D-048	none
`/rx-digest`	Weekly raw activity summary → `rx-meta/digest-YYYY-WW.md`	4-domain per-branch aggregation (finance via TradingV postgres post-D-046; degraded fallback to Lakshmi markdown)	none (cron-friendly)
`/rx-analyze`	Per-signal predictive power + source quality + weight-adjustment proposals	fitness Supabase + finance TradingV + learning markdown (3-domain since D-048; nutrition omitted until Phase J.2)	≥5 dispositioned recs AND ≥30% action-rate per domain — independent per-domain gate (D-018, D-030, D-048)
`/rx-goals` new D-049	Cross-door goal-progress meta tracker — elapsed vs progress drift per goal; READ-ONLY status, NOT recs	Zeus goals.yaml + Lakshmi goals_by_horizon.md + net_worth_snapshot.md + Ganesh learning_goals.md + active_sprints.md (3 doors; Athena explicitly skipped — body_recomp tracked via Zeus)	none — weekly notification scheduled Monday 09:00 CET via `mcp__scheduled-tasks` (`taskId=rx-goals-weekly`)

← prev

03 · Pipeline

05 · Feedback